{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6X5MM3TY2JISC6BPXOCGRLBJ7W","short_pith_number":"pith:6X5MM3TY","schema_version":"1.0","canonical_sha256":"f5fac66e78d25121782fbb8468ac29fd9f87e7a5edef76910dc79919f368fe06","source":{"kind":"arxiv","id":"2606.07653","version":1},"attestation_state":"computed","paper":{"title":"A Dataset for Dynamic Human Preferences for Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dylan Hadfield-Menell (Massachusetts Institute of Technology), Hannah Gao (Massachusetts Institute of Technology), Rachel Ma (Massachusetts Institute of Technology)","submitted_at":"2026-06-02T23:08:29Z","abstract_excerpt":"Given the increased adoption of Vision Language Models (VLMs) in human-interactive settings, it is important that we evaluate how well these models can adapt to real-time preferences for different users. While an increasing number of vision-language benchmarks have recently been introduced, they focus largely on evaluating static capabilities and generally-held preferences learned from extensive training data. This work introduces a new benchmark for evaluating the ability of VLMs to understand dynamic human-preferences, i.e. preferences that are passed in-context at inference time. We provide"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.07653","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T23:08:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7590dd621aaaa0090cece0b6885300d769615eedac504d8b84a27c42b968403d","abstract_canon_sha256":"b20c8617ceb0af5d2d5c07797b72453e2f5dfb92a698f22905a4b76f744731d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T00:04:45.895581Z","signature_b64":"qLOUP0Z5QGbgfVZqCJ8T8INWa0dVv0WcWvHaeR59V8b/78w/I8Rp80IvcyFWIzA3TQuCFO04yp74M1OwLdeFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5fac66e78d25121782fbb8468ac29fd9f87e7a5edef76910dc79919f368fe06","last_reissued_at":"2026-06-09T00:04:45.895164Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T00:04:45.895164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Dataset for Dynamic Human Preferences for Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dylan Hadfield-Menell (Massachusetts Institute of Technology), Hannah Gao (Massachusetts Institute of Technology), Rachel Ma (Massachusetts Institute of Technology)","submitted_at":"2026-06-02T23:08:29Z","abstract_excerpt":"Given the increased adoption of Vision Language Models (VLMs) in human-interactive settings, it is important that we evaluate how well these models can adapt to real-time preferences for different users. While an increasing number of vision-language benchmarks have recently been introduced, they focus largely on evaluating static capabilities and generally-held preferences learned from extensive training data. This work introduces a new benchmark for evaluating the ability of VLMs to understand dynamic human-preferences, i.e. preferences that are passed in-context at inference time. We provide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07653","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.07653/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.07653","created_at":"2026-06-09T00:04:45.895229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07653v1","created_at":"2026-06-09T00:04:45.895229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07653","created_at":"2026-06-09T00:04:45.895229+00:00"},{"alias_kind":"pith_short_12","alias_value":"6X5MM3TY2JIS","created_at":"2026-06-09T00:04:45.895229+00:00"},{"alias_kind":"pith_short_16","alias_value":"6X5MM3TY2JISC6BP","created_at":"2026-06-09T00:04:45.895229+00:00"},{"alias_kind":"pith_short_8","alias_value":"6X5MM3TY","created_at":"2026-06-09T00:04:45.895229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6X5MM3TY2JISC6BPXOCGRLBJ7W","json":"https://pith.science/pith/6X5MM3TY2JISC6BPXOCGRLBJ7W.json","graph_json":"https://pith.science/api/pith-number/6X5MM3TY2JISC6BPXOCGRLBJ7W/graph.json","events_json":"https://pith.science/api/pith-number/6X5MM3TY2JISC6BPXOCGRLBJ7W/events.json","paper":"https://pith.science/paper/6X5MM3TY"},"agent_actions":{"view_html":"https://pith.science/pith/6X5MM3TY2JISC6BPXOCGRLBJ7W","download_json":"https://pith.science/pith/6X5MM3TY2JISC6BPXOCGRLBJ7W.json","view_paper":"https://pith.science/paper/6X5MM3TY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07653&json=true","fetch_graph":"https://pith.science/api/pith-number/6X5MM3TY2JISC6BPXOCGRLBJ7W/graph.json","fetch_events":"https://pith.science/api/pith-number/6X5MM3TY2JISC6BPXOCGRLBJ7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6X5MM3TY2JISC6BPXOCGRLBJ7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6X5MM3TY2JISC6BPXOCGRLBJ7W/action/storage_attestation","attest_author":"https://pith.science/pith/6X5MM3TY2JISC6BPXOCGRLBJ7W/action/author_attestation","sign_citation":"https://pith.science/pith/6X5MM3TY2JISC6BPXOCGRLBJ7W/action/citation_signature","submit_replication":"https://pith.science/pith/6X5MM3TY2JISC6BPXOCGRLBJ7W/action/replication_record"}},"created_at":"2026-06-09T00:04:45.895229+00:00","updated_at":"2026-06-09T00:04:45.895229+00:00"}